Exploiting Channel Similarity for Accelerating Deep Convolutional Neural Networks

TL;DR

This paper introduces a novel channel pruning method for deep CNNs that groups similar channels based on a probabilistic similarity metric, enabling effective acceleration without complex training procedures.

Contribution

It proposes a new channel similarity metric and a hierarchical clustering-based pruning algorithm that can be applied directly to pre-trained models, improving acceleration performance.

Findings

Achieves 30% FLOPs reduction on ImageNet with ResNet-50

Outperforms previous pruning methods in acceleration efficiency

Does not require sparsity training or complex optimization

Abstract

To address the limitations of existing magnitude-based pruning algorithms in cases where model weights or activations are of large and similar magnitude, we propose a novel perspective to discover parameter redundancy among channels and accelerate deep CNNs via channel pruning. Precisely, we argue that channels revealing similar feature information have functional overlap and that most channels within each such similarity group can be removed without compromising model's representational power. After deriving an effective metric for evaluating channel similarity through probabilistic modeling, we introduce a pruning algorithm via hierarchical clustering of channels. In particular, the proposed algorithm does not rely on sparsity training techniques or complex data-driven optimization and can be directly applied to pre-trained models. Extensive experiments on benchmark datasets strongly demonstrate the superior acceleration performance of our approach over prior arts. On ImageNet, our pruned ResNet-50 with 30% FLOPs reduced outperforms the baseline model.